© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 97326
    Prev
    Next
    INDEX
    Explanations

    structured data elements and references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    citations and highlighted phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    majánló
    -0.73
    tvguidetime
    -0.69
    mpagne
    -0.68
    ipheral
    -0.66
     econômica
    -0.63
    ܃
    -0.63
    最快更新
    -0.63
     мәкал
    -0.61
     surla
    -0.61
    toThrow
    -0.60
    POSITIVE LOGITS
    WEBPACK
    0.42
    Хьажоргаш
    0.31
    principalTable
    0.31
    Override
    0.30
     BoxDecoration
    0.30
    parametrize
    0.28
    OptionsMenu
    0.28
    invokeLater
    0.27
     Comprometido
    0.27
     ureter
    0.26
    Activations Density 0.057%

    No Known Activations